Jiqing Expressway Dataset

这个数据集是一个多车道检测数据集，可用于测试和评估多种车道检测算法。数据集由中国济南至青岛高速公路部分路段的路面交通记录器采集，车道采用半手动方法（下文描述）进行标注。数据集包含40个视频片段，每个片段时长3分钟，帧率为30fps，视频分辨率为1920×1080。总共包含210610张不同光照强度和不同路况（上游、下坡、隧道、涵洞、匝道等）的道路图像。

This dataset is a multi-lane detection dataset that can be used to test and evaluate various lane detection algorithms. It was collected from road traffic recorders on selected sections of the Jinan-Qingdao Expressway in China. The lanes are annotated via a semi-manual method as described below. The dataset contains 40 video clips, each with a duration of 3 minutes, a frame rate of 30 fps, and a resolution of 1920×1080. In total, it includes 210,610 road images captured under varying lighting conditions and diverse road scenarios, including uphill sections, downhill sections, tunnels, culverts, ramps, and other similar scenarios.

搜集汇总

背景与挑战

背景概述

Jiqing Expressway Dataset是一个高速公路多车道检测数据集，包含40段3分钟视频(共210,610帧)，涵盖不同光照和路况条件，视频分辨率为1920×1080，适用于车道检测算法的测试评估。